Hi,
Please find a patch attached which adds missing sql error code in
error reports which are FATAL or PANIC, in xlogrecovery.
This will help with deducing patterns when looking at error reports
from multiple postgres instances.
--
Thanks and Regards,
Krishnakumar (KK).
[Microsoft]
From 4cc518f25710c512ba3f9452392dc6ea67c2248b Mon Sep 17 00:00:00 2001
From: "Krishnakumar R (KK)" <kksrcv...@gmail.com>
Date: Thu, 30 Nov 2023 00:56:40 -0800
Subject: [PATCH v1] Add missing error codes to PANIC/FATAL error reports.
---
src/backend/access/transam/xlogrecovery.c | 45 +++++++++++++++--------
1 file changed, 30 insertions(+), 15 deletions(-)
diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c
index c61566666a..2f50928e7e 100644
--- a/src/backend/access/transam/xlogrecovery.c
+++ b/src/backend/access/transam/xlogrecovery.c
@@ -630,7 +630,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
if (!ReadRecord(xlogprefetcher, LOG, false,
checkPoint.ThisTimeLineID))
ereport(FATAL,
- (errmsg("could not find redo location referenced by checkpoint record"),
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("could not find redo location referenced by checkpoint record"),
errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n"
"If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n"
"Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.",
@@ -640,7 +641,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
else
{
ereport(FATAL,
- (errmsg("could not locate required checkpoint record"),
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("could not locate required checkpoint record"),
errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n"
"If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n"
"Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.",
@@ -764,7 +766,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
* simplify processing around checkpoints.
*/
ereport(PANIC,
- (errmsg("could not locate a valid checkpoint record")));
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("could not locate a valid checkpoint record")));
}
memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint));
wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN);
@@ -817,7 +820,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
*/
switchpoint = tliSwitchPoint(ControlFile->checkPointCopy.ThisTimeLineID, expectedTLEs, NULL);
ereport(FATAL,
- (errmsg("requested timeline %u is not a child of this server's history",
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("requested timeline %u is not a child of this server's history",
recoveryTargetTLI),
errdetail("Latest checkpoint is at %X/%X on timeline %u, but in the history of the requested timeline, the server forked off from that timeline at %X/%X.",
LSN_FORMAT_ARGS(ControlFile->checkPoint),
@@ -833,7 +837,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
tliOfPointInHistory(ControlFile->minRecoveryPoint - 1, expectedTLEs) !=
ControlFile->minRecoveryPointTLI)
ereport(FATAL,
- (errmsg("requested timeline %u does not contain minimum recovery point %X/%X on timeline %u",
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("requested timeline %u does not contain minimum recovery point %X/%X on timeline %u",
recoveryTargetTLI,
LSN_FORMAT_ARGS(ControlFile->minRecoveryPoint),
ControlFile->minRecoveryPointTLI)));
@@ -861,12 +866,14 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
checkPoint.newestCommitTsXid)));
if (!TransactionIdIsNormal(XidFromFullTransactionId(checkPoint.nextXid)))
ereport(PANIC,
- (errmsg("invalid next transaction ID")));
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("invalid next transaction ID")));
/* sanity check */
if (checkPoint.redo > CheckPointLoc)
ereport(PANIC,
- (errmsg("invalid redo in checkpoint record")));
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("invalid redo in checkpoint record")));
/*
* Check whether we need to force recovery from WAL. If it appears to
@@ -877,7 +884,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
{
if (wasShutdown)
ereport(PANIC,
- (errmsg("invalid redo record in shutdown checkpoint")));
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("invalid redo record in shutdown checkpoint")));
InRecovery = true;
}
else if (ControlFile->state != DB_SHUTDOWNED)
@@ -953,7 +961,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
if (dbstate_at_startup != DB_IN_ARCHIVE_RECOVERY &&
dbstate_at_startup != DB_SHUTDOWNED_IN_RECOVERY)
ereport(FATAL,
- (errmsg("backup_label contains data inconsistent with control file"),
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("backup_label contains data inconsistent with control file"),
errhint("This means that the backup is corrupted and you will "
"have to use another backup for recovery.")));
ControlFile->backupEndPoint = ControlFile->minRecoveryPoint;
@@ -1664,7 +1673,8 @@ PerformWalRecovery(void)
if (record->xl_rmid != RM_XLOG_ID ||
(record->xl_info & ~XLR_INFO_MASK) != XLOG_CHECKPOINT_REDO)
ereport(FATAL,
- (errmsg("unexpected record type found at redo point %X/%X",
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("unexpected record type found at redo point %X/%X",
LSN_FORMAT_ARGS(xlogreader->ReadRecPtr))));
}
else
@@ -1792,7 +1802,8 @@ PerformWalRecovery(void)
{
if (!reachedConsistency)
ereport(FATAL,
- (errmsg("requested recovery stop point is before consistent recovery point")));
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("requested recovery stop point is before consistent recovery point")));
/*
* This is the last point where we can restart recovery with a new
@@ -1850,7 +1861,8 @@ PerformWalRecovery(void)
recoveryTarget != RECOVERY_TARGET_UNSET &&
!reachedRecoveryTarget)
ereport(FATAL,
- (errmsg("recovery ended before configured recovery target was reached")));
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("recovery ended before configured recovery target was reached")));
}
/*
@@ -2324,7 +2336,8 @@ checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, TimeLineID prevTLI,
/* Check that the record agrees on what the current (old) timeline is */
if (prevTLI != replayTLI)
ereport(PANIC,
- (errmsg("unexpected previous timeline ID %u (current timeline ID %u) in checkpoint record",
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("unexpected previous timeline ID %u (current timeline ID %u) in checkpoint record",
prevTLI, replayTLI)));
/*
@@ -2333,7 +2346,8 @@ checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, TimeLineID prevTLI,
*/
if (newTLI < replayTLI || !tliInHistory(newTLI, expectedTLEs))
ereport(PANIC,
- (errmsg("unexpected timeline ID %u (after %u) in checkpoint record",
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("unexpected timeline ID %u (after %u) in checkpoint record",
newTLI, replayTLI)));
/*
@@ -2349,7 +2363,8 @@ checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, TimeLineID prevTLI,
lsn < minRecoveryPoint &&
newTLI > minRecoveryPointTLI)
ereport(PANIC,
- (errmsg("unexpected timeline ID %u in checkpoint record, before reaching minimum recovery point %X/%X on timeline %u",
+ (errcode(ERRCODE_DATA_CORRUPTED),
+ errmsg("unexpected timeline ID %u in checkpoint record, before reaching minimum recovery point %X/%X on timeline %u",
newTLI,
LSN_FORMAT_ARGS(minRecoveryPoint),
minRecoveryPointTLI)));
--
2.40.1
